typos again

Author: qgeissmann

report/intro.tex

@@ -34,7 +34,7 @@ \section{Introduction} \label{intro}
 The quality of the acquisition can also be made considerably worst by noisy signals or by the presence of artefacts.
 For these reasons, sleep scoring, \ie{} the attribution of discrete vigilance states to electrophysiological time series,
 is traditionally performed by trained human experts.
-Such manual annotation is very time consuming; several hours of work have been reported in order to score 24h of recording.
+Such manual annotation is very time consuming; several hours of work have been reported in order to score 24h of recording\cite{sunagawa_faster:_2013}.
 This severely limits data throughput, and human subjectivity is likely to introduce systematic bias.
 Indeed, it is expected that scoring will be performed differently by each expert, making result difficult to reproduce independently.
 Often, two experts score the same data, in order to ensure satisfying agreement.
@@ -88,14 +88,14 @@ \section{Introduction} \label{intro}
 An important addition was the computation of time-aware
 features\cite{dietterich_machine_2002,deng_time_2013} which significantly improved
 accuracy. 
-Indeed, since manual scorers usually use contextual information (personal communications) to make a decision concerning a given state,
+Indeed, since manual scorers usually use contextual information to make a decision concerning a given state (personal communications),
 it was important to build a predictor that could be time-aware.
 Furthermore, as opposed to previous work, stratified cross-validation\cite{ding_querying_2008} procedure and
 comparisons of resulting sleep patterns were performed.
 These improvement altogether contributed to achieve a very satisfying overall accuracy of 92\% compared to manual scoring.
 
 
-In order to pave the way to an implementation of an ubiquitous sleep scoring software.
+In order to pave the way to the implementation of an ubiquitous sleep scoring software.
 \pr, a new \py{} package was also build to facilitate efficient feature extraction.
 This new package is here demonstrated to perform significantly better than \pyeeg{}\cite{bao_pyeeg:_2011}; an alternative implementation.
 In addition, inconsistencies in the implementations of some algorithms were corrected, and many new features were developed.

report/report.tex

@@ -127,7 +127,7 @@
 mammals such as rodents.
 Historically, labelling of EEG recordings has been performed visually by trained
 human experts. This task is extremely tedious an quite subjective.   
-Despite recent efforts to develop a automatic classifier of sleep stages
+Despite recent efforts to develop a automatic classifier of sleep stages,
 little adoption has occurred, and manual scoring is still the standard.
 
 This study presents a high accuracy classifier of sleep stage that